用复杂背景让大模型更真实地模拟人类群体行为
Identity, Cooperation and Framing Effects within Groups of Real and Simulated Humans
- 给大模型注入丰富叙事身份，提升行为仿真精度
- 可精准复现时间、问题表述等上下文对决策的影响
- 适合研究社会心理学实验中的隐藏变量
人类行为受理性判断与身份、情境因素共同影响。本文研究大语言模型（LLMs）在社会困境游戏场景中模拟人类行为的能力。以往工作仅通过‘引导’（弱绑定）使对话模型扮演角色，而本文探讨将基础模型进行深度绑定，融入扩展的背景故事，以实现更真实的基于身份的行为再现。结果表明，通过丰富的情境化身份设定，并使用指令微调模型验证一致性，可显著提升模型模拟与真人实验的一致性。同时，大模型能有效建模时间（实验年份）、问题表述方式及参与者群体等上下文因素。因此，该方法可揭示常被实验描述忽略但影响人类行为的关键细节，助力研究的准确复现。
原文摘要 · Abstract (English)
Humans act via a nuanced process that depends both on rational deliberation and also on identity and contextual factors. In this work, we study how large language models (LLMs) can simulate human action in the context of social dilemma games. While prior work has focused on "steering" (weak binding) of chat models to simulate personas, we analyze here how deep binding of base models with extended backstories leads to more faithful replication of identity-based behaviors. Our study has these findings: simulation fidelity vs human studies is improved by conditioning base LMs with rich context of narrative identities and checking consistency using instruction-tuned models. We show that LLMs can also model contextual factors such as time (year that a study was performed), question framing, and participant pool effects. LLMs, therefore, allow us to explore the details that affect human studies but which are often omitted from experiment descriptions, and which hamper accurate replication.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。